JP2006085678A - Image generation method, image generation apparatus, and image generation program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To generate a reverse-aging image representing a skin part of a person in reverse aging by using an image of the skin part of the person at a predetermined age. <P>SOLUTION: A wrinkle component extraction means 30 of an image generation unit 60 extracts wrinkle components Qm (m=1 to n) in a plurality of frequency bands of a face image D0 of the person obtained at the time of authentication of the person. A reverse-aging image generation means 40 obtains the reverse-aging image by subtracting from the face image D0 an adjustment component obtained by multiplication of a sum of the wrinkle components by an adjustment coefficient ρ determined by pixel values of the face image D0, a reverse-aging period from the current age at the time of the authentication to the age at the time of registration to a database, an age group in the reverse-aging period, and face parts. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an image creating method and apparatus for creating a skin part image after aging and a skin part image at the time of aging of a person using a skin part image such as a human face, and a program therefor. Is.

  In the human face, the skin, such as the neck, hands, etc., the wrinkles, stains, etc. (hereinafter referred to as “increased amount and / or increased intensity. A wrinkle component). Conventionally, various processes using the relationship between wrinkle components and age have been proposed. In Patent Document 1, a wrinkled part image and a wrinkle-free part image are created for each face part such as the eye circumference, forehead, mouth circumference, nose lip groove, and cheek in the face. A face image obtained by applying a wrinkle-free part image and a wrinkle-free part image to each part of the face, such as a combination of a no-frame image, a wrinkle-free mouth area image, a wrinkled nose lip image, and a wrinkled cheek image A system has been proposed for simulating the effect on the visual impression (visual age and attractiveness) depending on whether or not there are wrinkles in each part.

  Also, in Patent Document 2, facial parts having feature quantities (for example, wrinkles, acne, rough skin) corresponding to age are prepared in advance, and face images corresponding to age are created by combining these facial parts. A system has also been proposed.

  On the other hand, with the progress of image recognition technology, a system has also been proposed that performs authentication by recognizing a person's face and comparing it with a pre-registered face image (for example, see Non-Patent Document 1). These authentication systems implement authentication by performing pattern matching between the face image of the target person and the face image stored in the database.

  In addition, a skin beautification process that suppresses and removes wrinkles and spots from a photographic image including a human face has been conventionally performed. For example, a wrinkle component is removed by applying a low pass filter (LPF) that is normally used for noise removal. However, LPF can suppress wrinkles, stains, and noise components from an image, but has a drawback of degrading an edge portion in an image signal and blurring the entire image.

  Also, it was devised to separate and suppress small-amplitude high-frequency noise components in the image by utilizing the fact that many components such as wrinkles and spots exist as small-amplitude signals in the high-frequency components of the image. In addition, an ε-filter (ε-separated non-linear digital filter) is also applied to remove wrinkles and spots (Non-Patent Document 2). Since the ε-filter has the property of flattening only small amplitude level changes in the image signal, the image processed using the ε-filter preserves edges with steep level changes, and The sharpness of the is almost not impaired.

The ε-filter basically serves to subtract a value obtained by applying a nonlinear function to the amount of change in amplitude level from the original image signal. This nonlinear function is a function that sets the output to 0 when the amplitude of the signal is larger than a predetermined threshold. The output of this nonlinear function is considered to correspond to the wrinkle component in the image. That is, when the ε-filter is applied, the output of the nonlinear function is 0 at a portion in the image where the amplitude is larger than the above-mentioned threshold value. In the processed image, the original signal of the part is retained. On the other hand, in the part where the amplitude is equal to or smaller than the threshold value, in the processed image, the signal value of the part is output from the original signal value as a nonlinear function. (The absolute value is greater than 0). By doing this, although it is not so-called noise, in the wrinkles and spots such as wrinkles that show small amplitude light and dark changes, the light and dark changes are smoothed, and wrinkles and spots can be made inconspicuous, and edges with large amplitude Can hold the part.
JP 2002-304619 A JP-A-6-333005 "Face recognition system using facial images", IEICE Technical Report PRMU 97-50, June 1997, by Yamaguchi et al. Arakawa et al., "Color face image processing with vector ε-filter-Removal of flaw components" March 1998 Proceedings of the IEICE General Conference, D-11-43, PP143-

  However, since the human face is different in skin condition such as the strength and weakness of the wrinkle component with aging, it is registered in advance with the current face image of the target person as described in Non-Patent Document 1. In a system that performs authentication by pattern matching with a person's face image, there is a problem that the accuracy of the authentication is lost when the number of years has passed since the registration of the face image. Therefore, it is conceivable to update the registration of facial images at an appropriate time, but the registration update work becomes a huge burden when the number of registered people increases, and the system aims to find criminals. In some cases, registration update work is often impossible, which is unrealistic.

  Therefore, instead of updating the registration of the face image, for example, a face image corresponding to the age of the target person at the time of authentication is created by combining face part images corresponding to the age as in the method described in Patent Document 2. Can be used for authentication. In this case, since the face part image corresponding to the age of the target person at the time of authentication is unrealistic to be acquired by registration, for the same reason as described above, for example, a large number of persons with different age groups (referred to as sample persons) ) Face parts images are prepared in advance, and at the time of authentication, it is conceivable to create face images of the target person by selecting face part images that are similar in contour to the target person's face parts and close in age. However, although the outline is similar, the authentication using the created face image is not highly accurate as long as it is not an image of the target person's face part. Since the strength is different, there is a problem that the face image of the target person created from the face part image of the sample person may be far away from the actual face of the target person, further degrading the accuracy of authentication. Therefore, it is expected that a face image of the person after aging is created from the registered target person's face image.

  In addition, not only in the authentication system but also in a simulation system such as that described in Patent Document 1, it is expected that a facial part image corresponding to the age of the person can be simulated. The amount and strength of the wrinkle component varies depending on the age, and the simulation system described in Patent Document 1 that combines only wrinkle-free and wrinkle-free face parts has an effect on whether or not the corresponding parts of the face parts have wrinkles. Although it can be confirmed, it cannot be simulated according to age. Not only wrinkled and wrinkle-free face parts, but also, for example, create wrinkled face parts according to the age of the current age, and combine these face parts to simulate changes in facial impressions with age. In order to realize such a simulation system, it is necessary to create a face part image corresponding to the age.

  The present invention has been made in view of the above circumstances, and it is possible to create an image at a time different from the predetermined age by using an image of a face of a person at a predetermined age or a part of the face. An object of the present invention is to provide a method and apparatus for creating an image and a program therefor.

The image processing method of the present invention uses an image of a skin part of a person of a predetermined age as an actual-age image, and an aging image that becomes an image of the skin part after aging of the person and / or a reduction of the person In an image creation method for creating an aged image that becomes an image of the skin part at the time of age,
Extracting from the current age image as an age component a component capable of showing a skin condition that increases with an increase in age,
Adjusting the age component with a predetermined adjustment strength to obtain an adjustment component,
In the creation of the aging image, the adjustment component is added to the current age image, and in the creation of the age-reduced image, the adjustment component is subtracted from the current age image.

  Here, “after aging” means after a lapse of time from the predetermined age, and “when aging” is contrary to the “after aging”, It means that it is earlier than the predetermined age, going back from the age.

  Also, “increasing with increasing age” means increasing quantity and / or increasing intensity, ie enhancement.

  Examples of the age component include a wrinkle component and / or a stain component (hereinafter generally referred to as a wrinkle component).

As a method of extracting the wrinkle component as the age component, for example, based on the current age image, create a plurality of band limited images representing components for each of a plurality of frequency bands of the current age image,
For an input value in which the absolute value of the output value is less than or equal to the absolute value of the input value and the absolute value is less than or equal to a predetermined threshold value, the absolute value of the output value increases as the absolute value of the input value increases. On the other hand, for an input value whose absolute value is larger than the predetermined threshold value, nonlinear conversion processing in which the absolute value of the output value is equal to or smaller than the absolute value of the output value corresponding to the predetermined threshold value is performed for each band limitation. Apply to each pixel value of the image to get the pixel values of multiple converted images,
It is preferable to obtain an added pixel value obtained by adding pixel values of corresponding pixels of the plurality of converted images as a pixel value of an age component image representing the age component.

  Further, the pixel value of the age component image thus obtained can be multiplied by an adjustment coefficient indicating the adjustment intensity to obtain an image value of the image representing the adjustment component.

  The same adjustment coefficient may be used for each pixel, but it is preferable that the adjustment coefficient is determined according to the pixel value of the current age image.

  In the image creating method according to the present invention, if the adjustment strength is such that the adjustment component is increased as the degree of aging or aging increases, the degree of aging or reduction from the current age image is used. An image according to the age can be created. Here, the degree of aging or aging can be the length of the aging or aging period, for example, the number of years.

  In addition, the degree of change of age components such as wrinkle components in the skin portion of a person depends not only on the degree of aging or aging, that is, the length of the period, but also on the age period or the age group of the aging period. Is also different. For example, in the case of aging for the same five years, if the amount of increase in wrinkle component when aging from 20 to 25 is 1, then when aging from 25 to 30 years, from 30 to 35 years In the case of aging in the age of 35 to 40 years of age, or in the case of aging between the ages of 40 and 45, the amount of increase in the wrinkle component is 1.15, 1.15, 1.2, 1. 1, the degree of increase in the wrinkle component varies depending on the age group of the aging period. Similarly, in the case of aging, if the amount of wrinkle reduction when aging from 25 to 20 is 1, the aging from 45 to 40, the age from 40 to 35 When the age is decreased from 35 to 30 years old, and when the age is decreased from 30 to 25 years old, the amount of reduction of the wrinkle component is 1.1, 1.2.1.15 and 1.15, respectively. In addition, the amount of wrinkle reduction is different depending on the age group of the aging period. The image creating method of the present invention takes such matters into consideration, and the adjustment strength includes not only the length of the aging or aging period but also the age of the aging period or the aging period. It is preferable to use one determined according to the layer, and by doing so, a more appropriate aging image or aging image can be obtained.

  Furthermore, the degree of change in age components such as wrinkle components in a person's skin varies depending on the part of the person's body. For example, even in the same aging period (length of period, age group of period), the degree of increase in the wrinkle component of the hand part is small compared to the whole face, while the wrinkle of the neck part is smaller than that of the hand part. There is a tendency that the degree of increase in the component is small. In addition, in the face, even if the aging period is the same, the degree of increase in wrinkle components with aging differs depending on the facial parts such as the corners of the eyes, the forehead, and the jaw. Of course, the same applies to the case of aging. In the image creation method of the present invention, it is preferable that the skin strength is determined according to a part of the person's body as the adjustment strength.

The image creating apparatus according to the present invention uses an image of a skin part of a person of a predetermined age as an actual-age image, and an aging image that becomes an image of the skin part after aging of the person and / or a reduction of the person In an image creation device for creating an aged image that becomes an image of the skin part at the time of aging,
Age component extraction means for extracting from the current age image as an age component a component capable of showing a skin condition that increases with an increase in age;
Adjustment component acquisition means for adjusting the age component at a predetermined adjustment intensity to obtain an adjustment component;
Image adjustment means for acquiring the aging image by adding the adjustment component to the current age image, and subtracting the adjustment component from the current age image to acquire the aging image. It is a feature.

The age component can be a wrinkle component and / or a wrinkle component (generally referred to as a wrinkle component), and the age component extraction means for extracting the wrinkle component is based on the current age image, Create multiple band-limited images that represent components for multiple frequency bands,
For an input value in which the absolute value of the output value is less than or equal to the absolute value of the input value and the absolute value is less than or equal to a predetermined threshold value, the absolute value of the output value increases as the absolute value of the input value increases. On the other hand, for an input value whose absolute value is larger than the predetermined threshold value, nonlinear conversion processing in which the absolute value of the output value is equal to or smaller than the absolute value of the output value corresponding to the predetermined threshold value is performed for each band limitation. Apply to each pixel value of the image to get the pixel values of multiple converted images,
It is preferable that an added pixel value obtained by adding pixel values of corresponding pixels of the plurality of converted images is acquired as a pixel value of an age component image representing the age component.

  In this case, the adjustment component acquisition unit may multiply the pixel value of the age component image by an adjustment coefficient indicating the adjustment intensity to obtain an image value of the image representing the adjustment component.

  Moreover, it is preferable that the said adjustment coefficient is determined for every said pixel according to the pixel value of the pixel of the said age image.

  It is preferable that the adjustment strength increases the adjustment component as the degree of aging or aging increases.

  Furthermore, the adjustment strength is more preferably determined according to the age group of the aging period or the aging period.

    The adjustment strength is determined by the skin part being the part of the person's body, the age component, the presence / absence of makeup in the current image, the presence / absence of makeup when creating an aging image or aged image, and the color of the person's skin. More preferably, it is determined accordingly.

  The program of the present invention causes a computer to execute the image processing method of the present invention.

  An image creation method and apparatus according to the present invention and a program therefor are an adjustment component obtained by extracting an age component such as a wrinkle component from an actual age image of a person's skin and adjusting the age component with a predetermined adjustment coefficient. Are added to or subtracted from the current age image to obtain an aging image or an aging image. Since the aging image or the aging image is created from the current age image of the person, it is not affected by individual differences in the appearance of the age component.

  In addition, by using the degree of adjustment for adjusting the age component, the length of the aging or aging period, the age group of the aging period or the aging period, the one determined according to the site, etc., An age-appropriate aging image or aged image can be appropriately obtained.

  Embodiments of the present invention will be described below with reference to the drawings.

  FIG. 1 is a block diagram showing a configuration of an authentication apparatus according to an embodiment of the present invention. Note that the authentication device of the present embodiment is realized by executing an authentication processing program read into the auxiliary storage device on a computer (for example, a personal computer). The authentication processing program is stored in an information storage medium such as a CD-ROM or distributed via a network such as the Internet and installed in a computer.

  Further, since the image data represents an image, the following description will be given without particularly distinguishing the image from the image data.

  As illustrated in FIG. 1, the authentication apparatus according to the present embodiment includes an imaging unit 1, an authentication unit 100, a first database 120, and a second database 140. The face image D0 is obtained by capturing an image of the target person, and the first database 120 stores the registered face image Dg of each person in association with the age at the time of registration. The database 140 of FIG. 2 stores various parameters provided to the authentication unit 100. The authentication unit 100 stores the face image D0, the registered face image Dg stored in the first database 120, and the second image. Authentication is performed using parameters stored in the database 140.

  2 is a block diagram illustrating a configuration of the authentication unit 100 in the authentication apparatus according to the embodiment illustrated in FIG. 1. As illustrated, the authentication unit 100 includes the input unit 2, the image generation unit 60, and the verification unit 70. The input unit 2 is for causing the person to be authenticated to input information that can identify the person (for example, the password P given to the person). 60 is a face when the age of the person is reduced from the age at the time of authentication to the age at the time of registration of the registered face image Dg of the person using the face image D0 of the person acquired by the imaging unit 1 An image (hereinafter referred to as an aged image) D1 is generated, and the collation unit 70 uses the registered face image Dg stored in the first database 120 and the aged image D1 generated by the image generation unit 60. Is used for verification.

  3 is a block diagram illustrating a configuration of the image generation unit 60 in the authentication unit 100 illustrated in FIG. 2. As illustrated, the image generation unit 60 includes the target specifying unit 3, the YCC conversion unit 5, and the blurred image. A creation means 10, a band-limited image creation means 20, a wrinkle component extraction means 30 for extracting a wrinkle component (hereinafter generally referred to as a wrinkle component), an aged image creation means 40, and a synthesis means 50 are provided. is there.

  The blurred image creating means 10 creates a plurality of blurred images S1, S2,... Sn (n: integer greater than or equal to 2) of the original image S0 having different frequency response characteristics. Is to create a plurality of band limited images T1, T2,... Tn using the original image S0 and the blurred images S1, S2,. , T2,... Tn are each subjected to non-linear transformation processing to extract wrinkle components Q1, Q2,... Qn in the frequency band corresponding to each band-limited image. Is used to create an aged image S′1 of the original image S0 using the original image S0 and the wrinkle components Q1, Q2,. Since these means perform processing in the luminance space, the YCC conversion means 5 performs YCC conversion on the face image D0 (R0, G0, B0) obtained by the imaging unit 1 to generate the face image D0. The luminance Y0 (the original image S0 described above is constituted by these luminance components Y0) and the color differences Cb0 and Cr0 are obtained, and the synthesizing means 50 is the aging image S ′ obtained by the aging image creating means 40. An aged image D1 (Y1, Cb0, Cr0) is obtained by synthesizing an image composed of the pixel value Y1 of 1 and the color differences Cb0 and Cr0 obtained by the YCC conversion means 5. Here, the detail of each structure of the image generation part 60 is demonstrated.

  The YCC conversion means 5 converts the R, G, and B values of the face image D0 into the luminance value Y and the color difference values Cb and Cr according to the following equation (1).

Y = 0.2990 × R + 0.5870 × G + 0.1140 × B
Cb = −0.1687 × R−0.3313 × G + 0.5000 × B + 128 (1)
Cr = 0.5000 × R−0.4187 × G−0.0813 × B + 128

The blur image creation unit 10 creates a plurality of blur images using the luminance value Y0 obtained by the YCC conversion unit 5. FIG. 4 is a block diagram illustrating a configuration of the blurred image creation unit 10. As shown in the figure, the blurred image creation means 10 performs filtering processing 12 that obtains filtered images B1, B2,... Bn obtained by performing thinning processing after performing filtering processing, and performs interpolation processing on each filtering image. The interpolation means 14 and the control means 16 for controlling the filtering means 12 and the interpolation means 14 are provided. The filtering means 12 performs a filtering process using a low-pass filter. As this low-pass filter, for example, a filter F substantially corresponding to a 5 × 1 grid-like one-dimensional Gaussian distribution as shown in FIG. 5 is used. be able to. This filter F has σ = 1 in the following equation (2).

  The filtering unit 12 performs the filtering process and the half-thinning process on the image in the x direction and the y direction with respect to the image to be processed using such a filter F, so that the entire image to be processed is processed. Perform filtering processing.

FIG. 6 shows details of processing that the control unit 16 of the blurred image creation unit 10 causes the filtering unit 12 and the interpolation unit 14 to perform. As shown in the figure, the filtering means 12 first performs a filtering process on the original image S0 (Y0) every other pixel using the filter F shown in FIG. 5, and then thins out pixels that have not been subjected to the filtering process. By this processing, a filtered image B1 (Y1) is obtained. The size of the filtering image B1 is 1/4 of the size of the original image S0 (1/2 in the x direction and y direction, respectively). Next, the filtering unit 12 also performs filtering processing by the filter F and thinning processing every other pixel on the filtering image B1 (Y1) to obtain a filtering image B2 (Y2). The filtering unit 12 repeats the filtering process by the filter F and the 1/2 thinning process to obtain n filtered images Bk (k = 1 to n). The size of the filtering image Bk has become a ^{1/2 2K} of the size of the original image S0. FIG. 7 shows the frequency characteristics of each filtered image Bk obtained by the filtering means 12 when n = 3 as an example. As shown in the figure, the response of the filtered image Bk is such that the higher the k, the higher the frequency component is removed.

  In the present embodiment, the filtering unit 12 performs the filtering process on the x direction and the y direction of the image by the filter F shown in FIG. 5, but the 5 × 5 2 as shown in FIG. 8. A filtering process may be performed on the original image S0 and the filtering image Bk at once by a dimension filter.

The interpolation unit 14 performs an interpolation process on each filtering image Bk obtained by the filtering unit 12 so that the size of each filtering image Bk is the same as that of the original image S0. There are various interpolation processing methods such as a B-spline method. In this embodiment, the filtering unit 12 uses a filter F based on a Gaussian signal as a low-pass filter. A Gaussian signal is also used as an interpolation coefficient for performing the interpolation calculation, and this interpolation coefficient is approximated to σ = 2 ^K−1 in the following equation (3).

When interpolating the filtering image B1, since k = 1, σ = 1. The filter for performing interpolation when σ = 1 in the above equation (3) is a 5 × 1 one-dimensional filter F1 as shown in FIG. The interpolation means 14 first expands the filtering image B1 to the same size as the original image S0 by inserting one pixel at a time every other pixel into the filtering image B1 to the same size as the original image S0. Then, a filtering process is performed by the filter F1 shown in FIG. 9 to obtain a blurred image S1. The blurred image S1 has the same number of pixels as the original image S0, that is, the same size as the original image S0.

  Here, the filter F1 shown in FIG. 9 is a 5 × 1 filter. However, before applying the filter F1, pixels having a value of 0 are inserted into the filtered image B1 every other pixel. The interpolation processing by the means 14 is substantially performed by two types of filters: a 2 × 1 filter (0.5, 0.5) and a 3 × 1 filter (0.1, 0.8, 0.1). Equivalent to filtering.

  When the interpolation means 14 performs interpolation on the filtered image B2, k = 2, so σ = 2. In the above equation (3), the filter corresponding to σ = 2 is an 11 × 1 one-dimensional filter F2 shown in FIG. The interpolation unit 14 first expands the filtering image B2 to the same size as the original image S0 by inserting three pixels each having a value of 0 every other pixel into the filtering image B2, and then expands the filtered image B2. Is subjected to a filtering process by a filter F2 shown in FIG. 10 to obtain a blurred image S2. The blurred image S2 has the same number of pixels as the original image S0, that is, the same size as the original image S0.

  Similarly, the filter F2 shown in FIG. 10 is an 11 × 1 filter, but before applying the filter F2, three pixels each having a value of 0 are inserted into the filtered image B2 every three pixels. Therefore, the interpolation processing by the interpolation means 14 is substantially performed by a 2 × 1 filter (0.5, 0.5) and a 3 × 1 filter (0.3, 0.65, 0.05), ( This is equivalent to filter processing using four types of filters (0.3, 0.74, 0.13) and (0.05, 0.65, 0.3).

Thus, the interpolation unit 14 inserts (2 ^K −1) pixels each having a value of 0 every other pixel into each filtering image Bk, thereby making the filtering image Bk the same as the original image S0. For a filtered image Bk that is enlarged to size and interpolated with pixels having a value of 0, the length created based on the above equation (3) is (3 × 2 ^K −1). A blurred image Sk is obtained by performing a filtering process.

  FIG. 11 shows the frequency characteristics of each blurred image Sk obtained by the blurred image creation means 10 when n = 3 as an example. As shown in the figure, the blurred image Sk is such that the higher the k, the higher frequency components of the original image S0 are removed.

  The band-limited image creating means 20 uses the blurred images S1, S2,... Sn obtained by the blurred image creating means 10 and components for each of a plurality of frequency bands of the original image S0 according to the following equation (4). .., Tn are generated.

Tm = S (m−1) −Sm (4)
Where m is an integer between 1 and n

FIG. 12 shows the frequency characteristics of each band limited image Tm obtained by the band limited image creating means 20 when n = 3 as an example. As illustrated, the band limited image Tm represents a component in the low frequency region of the original image S0 as m increases.

  The wrinkle component extraction unit 30 performs non-linear transformation on each band limited image Tm (m = 1 to n) obtained by the band limited image creating unit 20 to generate wrinkles in the frequency band corresponding to each band limited image Tm. , Spots, noise, and the like (hereinafter collectively referred to as wrinkle components) Q1, Q2,..., Qn. This non-linear transformation is a process of making the output value equal to or less than the input value, and for an input value less than or equal to a predetermined threshold value, the larger the input value, the larger the output value, but greater than the predetermined threshold value. For the input value, the output value is equal to or less than the output value corresponding to the predetermined threshold value. In this embodiment, the process is performed by a function f as shown in FIG. In the figure, the broken line indicates a function in which the output value = the input value, that is, the slope is 1. As shown in the figure, the nonlinear transformation function f used in the wrinkle component extraction unit 30 of the present embodiment has a slope of 1 when the absolute value of the input value is smaller than the first threshold Th1, and the absolute value of the input value. Is greater than or equal to the first threshold and less than or equal to the second threshold Th2, the slope is less than 1, and when the absolute value of the input value is greater than the second threshold Th2, the output value is the absolute value of the input value. This is a function having a constant value M smaller than the absolute value. The function f may be the same for each band limited image, but may be different for each band limited image.

  The wrinkle component extraction unit 30 uses the luminance value of each band limited image as an input value, performs nonlinear conversion on each band limited image using the nonlinear conversion function f shown in FIG. The configured wrinkle component Qm (m = 1 to n) in the frequency band corresponding to each band limited image is extracted and output to the aged image creating means 40.

  On the other hand, the object specifying means 3 changes the password P from the first database 120 (details of the first database 120 will be described later) based on the password P input via the input unit 2 of the authentication unit 100. The registered face image Dg stored correspondingly, the age at the time of registration of the person corresponding to the registered face image Dg, the date of registration, and the gender of the person are read out, and the registered face image Dg is read to the verification unit 70 of the authentication unit 100. On the other hand, information indicating the age at which the person corresponding to the registered face image Dg is registered (referred to as registered age), the gender of the person, and the registration date is output to the aged image creating means 40.

  FIG. 15 shows the contents of data in the first database 120. As shown in the figure, in the first database 120, the person's name, password, gender, registered face image Dg, age at registration, registration date Are stored in association with each other. The target specifying unit 3 reads the registered face image Dg and other data based on the password P of the person to be authenticated input via the input unit 2.

  The aged image creation means 40 includes an original image S0 obtained by the YCC conversion means 5, wrinkle components Q1, Q2,..., Qn in the original image S0 obtained by the wrinkle component extraction means 30, and a second A variety of parameters stored in the database 140 are used to create an aged image S′1 (Y1) of the original image S0, and FIG. 14 shows its configuration. As shown in the figure, the aged image creation means 40 includes a current age calculation unit 42, a parameter setting unit 44, and a creation execution unit 46.

  The current age calculation unit 42 calculates the current age (hereinafter referred to as the current age) of the person to be authenticated based on the registered age output from the target specifying unit 3 and the date at the time of authentication, and the parameter setting unit 44. Is output.

  The parameter setting unit 44 uses the current age of the person to be authenticated calculated by the current age calculation unit 42, the registered age of the person, and various parameters stored in the second database 140, so that the aging image The parameter W for creating S′1 (Y1) is set. Here, the processing by the parameter setting unit 44 will be described with reference to the second database 140 shown in FIG.

  As shown in FIG. 16, the second database 140 is further composed of three types of database A, database B, and database C.

  The database A stores the difference between the current age and the registered age, that is, the age N1 from the current age in association with the coefficient α corresponding to the age N1, and the coefficient α is In the example shown in the figure, the age of aging N1 is longer, and in the example shown in the drawing, 5 years or less, 5 years to 10 years or less, 10 years to 15 years or less, 15 to 20 years or less. It becomes 0.1, 0.2, 0.5, 0.6,. The parameter setting unit 44 first calculates the age of aging N1 based on the current age calculated by the current age calculating unit 42 and the registered age output from the target specifying means 3, and calculates the calculated age of aging. The coefficient α corresponding to N1 is read from the database A.

  The database B stores each stage (hereinafter referred to as the aging stage) N2 of the age group (aged age group) of the aging period in association with the adjustment rate γ0 corresponding to the aging stage N2. Is. As described above, the change of the person's wrinkle (increase or decrease. This “decrease” includes the meaning of both decrease in quantity and decrease in intensity as well as increase). Or, it depends on the age group of the aging period. In consideration of this, the database B of the second database 140 in the present embodiment divides the period of aging into a plurality of aging stages N2, and creates an adjustment rate γ0 for each aging stage N2. It is. In the example shown in the figure, the database B includes 45 to 40 years old, 40 to 35 years old, 35 to 30 years old, 30 to 25 years old age stages, 25 to 20 years old age stages N2 and The adjustment rate γ0 is stored correspondingly. First, the parameter setting unit 44 reads out the adjustment rates γ0 (1), γ (2),... At each stage N2 of the corresponding age group based on the registered age and the current age. Specifically, for example, when the current age at the time of authentication of a person whose registered age is 21 years old is 25 years old, in the example of the database B shown in FIG. Since only the age-declining stage N2 is applicable, only “1” is read as the adjustment rate γ0 (1) corresponding to the corresponding aging stage N2. On the other hand, when the current age of a person whose registered age is 31 years old is 44 years old, the age group of the age-reduced period is reduced by three from 45 to 40 years old, 40 to 35 years old, and 35 to 30 years old. Since it corresponds to the age stage N2, the adjustment rate γ0 (1), the adjustment rate γ0 (2), and the adjustment rate γ0 (3) corresponding to each corresponding aging stage N2 are “1.1”, “1.2”. ”And“ 1.15 ”are read out.

  The parameter setting unit 44 calculates a final adjustment rate γ using each read adjustment rate γ0 according to the following equation (5).

γ = γ0 (1) × γ0 (2) ×... γ0 (k) (5)
γ0: Adjustment rate γ: Final adjustment rate k: Number of read adjustment rates γ0

The database C stores the aging stage N3 and the adjustment rate δ0 for each facial part in association with the aging stage N3. The human face has different wrinkle component increases with age depending on the area of the corner of the eye, forehead, jaw, etc., for example, the wrinkle component in the forehead region tends to increase greatly during the period of 30 to 40 years old, After 40 years of age, wrinkle components in the chin and the corners of the eyes tend to increase greatly. In order to reflect such a tendency, the database C provides an adjustment rate δ0 for adjusting the coefficient α for each face part in accordance with the part and the aging stage N3. The parameter setting unit 44 checks whether the age group of the aging period between the current age and the registered age corresponds to the aging stage N3 shown in the database C, and if there is any, A process of reading out adjustment rates δ0 corresponding to all corresponding aging stages N3 and multiplying them to obtain a final adjustment rate δ, and obtaining the adjustment rate δ as 1 if there is no corresponding case Is determined for each site. For example, if the current age of a person whose registered age is 20 years old is 30 years old, the aging age group does not correspond to any aging stage N3 of the aging stage N3 of the database C shown in FIG. The site adjustment rate δ is set to 1. On the other hand, when the current age of a person whose registered age is 31 years old is 45 years old, the age group of the aging period corresponds to two aging stages N3 of -40 years old and 40-30 years old. For the forehead part, adjustment rates δ0 corresponding to the respective aging stages N3: “1” and “1.2” are read out, and the final adjustment rate δ for the forehead part is 1 × 1.2. “1.2” is acquired. For the jaw part, adjustment rates δ0: “1.2” and “1” corresponding to the respective aging stages N3 are read, and the final adjustment rate δ of the jaw part is 1.2 × 1. “1.2” is acquired. Furthermore, adjustment rates δ0 corresponding to the respective aging stages N3 are also read out for the eye corner region: “1.2” and “1”, and the final adjustment rate δ of the eye corner region is 1.2 × 1. “1.2” is acquired. For each other part, “1” is set as the final adjustment rate δ. For example, when the current age of a person whose registered age is 31 years old is 39 years old, the aging age group corresponds to one aging stage N3 of 40 to 30 years old. Is read out the adjustment rate δ0 corresponding to the aging stage N3: “1.2” to be the final adjustment rate δ of the forehead part, and corresponds to the aging stage N3 for the jaw part and the eye corner part Adjustment rate δ0 to be read: “1” is read out as the final adjustment rate δ, and “1” is set as the final adjustment rate δ for each of the other parts.

  Note that the second database 140 shown in FIG. 16 is an example of a woman, and in this embodiment, the second database 140 includes a database A, a database B, and a database C for male and female genders. The parameter setting unit 44 reads each parameter from the corresponding database according to the gender of the person to be authenticated.

  In this way, the parameter setting unit 44 obtains the adjustment rate γ obtained by multiplying the coefficient α read from the database A of the second database 140 by the adjustment rate γ0 read from the database B, and read from the database C. The adjustment rate δ for each part obtained by multiplying the adjustment rate δ0 is set and output to the creation execution unit 46 as the parameter W.

The creation execution unit 46 multiplies each wrinkle component Qm extracted by the wrinkle component extraction unit 30 by the adjustment coefficient ρ, and multiplies the wrinkle component Qm by the adjustment coefficient ρ (adjustment component). By subtracting from S0 (Y0), an aged image S′1 (Y1) is obtained. The following formulas (6) and (7) show processing performed by the aged image creating means 40.

ρ = β (S0) × α × γ × δ (7)
Where ρ: adjustment factor
β: Pixel value dependent coefficient
α: Coefficient read from database A
γ: Adjustment rate obtained by multiplying the adjustment rate γ0 read from the database B
δ: Adjustment rate obtained by multiplying the adjustment rate δ0 read from the database C

As described above, the coefficient α and the adjustment rate γ are the same for the entire original image S0, and the adjustment rate δ is set for each part of the face represented by the original image S0.

  The pixel value dependent coefficient β is β (S0), and is determined according to the luminance value Y0 of the pixel of the original image S0. Specifically, the larger the luminance value Y0 is, the larger the value of the coefficient β used when obtaining the pixel value Y1 of this pixel. The wrinkle component Qm extracted by the wrinkle component extraction means 30 may contain components such as hair, and when creating an aged image, the hair component is about the same as the true wrinkle component. It is desirable to avoid suppression (ie subtraction). In the present embodiment, focusing on the fact that the skin portion where wrinkles or the like are generally generated is bright (that is, the luminance value is large) and the hair portion is dark (that is, the luminance value is small), the pixel having the larger luminance value has a value. True wrinkles, spots or noise can be obtained by increasing the degree of subtraction of the skin part by using the coefficient β that increases (conversely, the value becomes smaller as the pixel has a lower luminance value), weakens the degree of subtraction of the hair part, and increases the degree of subtraction of the skin part. It can be suppressed by subtracting the components such as, and the suppression of the component representing the hair is weakened.

  The aged image creating means 40 of the image generating unit 60 outputs the aged image S′1 created in this way to the synthesizing means 50, and the synthesizing means 50 obtains the original image S0 obtained by the aged image creating means 40. The pixel value Y1 of the aging image S′1 and the color difference values Cb0 and Cr0 of the registered face image Dg obtained by the YCC conversion means 5 are combined to generate the aging image D1 (Y1, Cr0, Cb0) is obtained and output to the collation unit 70.

  The verification unit 70 of the authentication unit 100 includes the aged image D1 output from the image generation unit 60 (specifically, from the combining unit 50 of the image generation unit 60) and the registered face output from the target specifying unit 3. A pattern matching process is performed on the image Dg and collation is performed, and the process ends when the collation result is output.

  FIG. 17 is a flowchart showing processing performed in the authentication apparatus of the embodiment shown in FIG. As illustrated, when the face image D0 of the person to be authenticated obtained by the imaging unit 1 is acquired by the authentication device of the present embodiment (S10), the authentication unit 100 reads the authentication target from the first database 120. The registered face image Dg corresponding to the person, the age at the time of registration of the person corresponding to the registered face image Dg, the registration date, and the gender of the person are read (S12). Then, the authentication unit 100 extracts the wrinkle component Qm (m = 1 to n) from the face image D0 obtained by the imaging unit 1, and the registered age of the registered face image Dg, the age at the time of authentication (current age), Various parameters are read from the second database 140 based on gender and the like to obtain a coefficient α, an adjustment rate γ, and an adjustment rate δ for each part. The authentication unit 100 subtracts the adjustment component obtained by multiplying the sum total of the wrinkle component Qm by the coefficient α, the adjustment rate γ, the adjustment factor δ for each region, and the pixel value dependent coefficient β from the face image D0, and is an aging image. D1 is created (S14). Using the created aged image D1 and the registered face image Dg, the authentication unit 100 performs a collation process and outputs a collation result (S16), thereby terminating the process.

  As described above, according to the authentication device of the present embodiment, since the age-reduced image for authentication is created from the current-age image at the time of the authentication of the person, the age-reduced image has an individual difference in how the age component appears. Since it is not affected, accurate authentication can be performed.

  In addition, since the degree of adjustment for adjusting the age component is determined according to the length of the aging period, the age group of the aging period, the region, etc., a more appropriate aging image As a result, the accuracy of authentication can be further improved.

  In the authentication apparatus according to the present embodiment, components such as wrinkles and spots are present in each frequency band from a high frequency band to a low frequency band, although many components exist in the high frequency band. Paying attention, a plurality of band limited images Tm (m = 1 to n, n ≧ 2) representing components for a plurality of different frequency bands of the original image S0 (Y0) are created, and nonlinear with respect to these band limited images Conversion processing is performed to extract a plurality of converted images as wrinkle components. By doing so, it is possible to prevent the wrinkle component from leaking out, so that an appropriate aging image can be obtained by subtraction of the wrinkle component.

 Although one preferred embodiment of the present invention has been described above, the image creation method and apparatus of the present invention and the program therefor are not limited to the above-described embodiment, and various modifications can be made without departing from the gist of the present invention. Can increase, decrease, change.

  For example, the embodiment shown in FIG. 1 uses the image creation method and apparatus of the present invention for authentication of a person. When authentication is performed, an aged image is created from a face image at the time of authentication. However, the image creation method and apparatus of the present invention can be applied to an authentication system that creates an aging image and uses it for authentication. It can be applied to any system that requires age and / or age images.

  For example, like the authentication device of the embodiment shown in FIG. 1, an aging image is created from a face image at the time of authentication, and authentication is performed by comparing this aging image with a registered face image. On the other hand, an aging image is created from the registered face image based on the period from the registered age to the age at the time of authentication (age age corresponding to the above-mentioned aging age), and this aging image and authentication You may make it authenticate by collating with the face image of the time.

  Furthermore, a predetermined age (for example, intermediate age) between the registered age and the current age at the time of authentication is set as the reference age, and from the registered face image, an aging image is created when the reference age is reached, An aged image in the case of aging to this reference age may be created from the face image obtained at the time of authentication, and the aging image and the aged image may be used in the matching process. By doing so, the accuracy of authentication can be improved particularly when the difference between the registered age and the current age is large.

As shown in the following equation (8), the specific process of creating an aging image is performed by using an adjustment component obtained by multiplying the wrinkle component Qm extracted from the original image S0 by the adjustment coefficient ρ as the original image. Except for the point added to S0 and the database corresponding to the second database 140 for obtaining the adjustment coefficient ρ, except that the database created for aging is used, the same as the process for creating an aged image Therefore, specific processing for creating an aging image is omitted here.

In addition, the method for extracting the wrinkle component is not limited to the method used for the wrinkle component extracting unit 30 of the authentication apparatus according to the present embodiment, and any method that can extract the wrinkle component, for example, a method described in Non-Patent Document 2. May be applied.

  In the authentication apparatus of the present embodiment, the band limited image creating unit 20 obtains a band limited image according to the above formula (4) using the original image S0 and the blurred image Sk (k = 1 to n, n ≧ 2). The processing performed in the band-limited image creation means 20, the wrinkle component extraction means 30, and the aged image creation means 40 can be expressed by the following formula (9). For example, the following formula The band-limited image creation means, the wrinkle component extraction means, and the aged image creation means 40 may be processed according to (10), Expression (11), or Expression (12). That is, as in the processing in the authentication apparatus of the present embodiment represented by Expression (9), using the original image and each blurred image, images in the frequency bands adjacent to each other (the original image S0 is the same as the blurred image S1 and the frequency band The band-limited image may be obtained by performing subtraction of the adjacent image). However, as shown in Expression (10), the band-limited image is obtained by subtracting all the blurred images and the original image. Alternatively, as shown in Expression (11), a band-limited image may be obtained by subtracting blurred images in adjacent frequency bands without using the original image, or Expression (12). As shown in FIG. 5, the band-limited image is obtained by subtracting the blurred image S1 and all the blurred images Sm (m = 2 to n, n ≧ 3) excluding the blurred image S1 without using the original image. Also good.

Also, the method for creating the band limited image is to create a blurred image of the original image, and to create the blurred image of the original image and / or the blurred image as in the methods represented by the above formulas (4) and (9) to (12). The method is not limited to the method of creating using an image, and any method may be used as long as an image representing a plurality of different frequency band components of the original image can be created.

  Further, in this embodiment, since the image creation method and apparatus of the present invention are applied to authentication, an aged image is created from the face image D0 showing the entire face. The device is not limited to the creation of an aging image or an aging image of the entire face. For example, an aging image and an aging image (face part images of different ages) for each part such as around the eyes, cheeks, and forehead. By using the face part image created in this way, which can be applied to the creation of the above, in a system such as that described in Patent Document 1, simulation according to age can be performed.

  In addition, for example, only a face image of a character at a predetermined age is created, and an aging image or an aging is created and used from the face image according to a change in time according to the development of a story. It can also be applied to the field. In this case, the face image of a character at a predetermined age is not limited to one created using computer graphic technology, but may be a face photo image provided by a game player.

  Further, the image creation method and apparatus of the present invention is not limited to an image of a face or a part of a face, and any skin portion where an age component such as a wrinkle component increases or decreases according to age, such as a neck or a hand, is used. The present invention can also be applied to creation of an aging image or an aging image.

  By the way, in the above embodiment, the adjustment coefficient ρ changes according to the adjustment rates α, β, γ, and δ according to the above-described equation (7), but changes according to the adjustment rates ζ and η described below. You may do.

  For example, the adjustment coefficient ρ may be changed as shown in the following equation (13) according to the adjustment rate ζ indicating the wrinkle degree of the current age image.

ρ = β (S0) × α × γ × δ × ζ (13)
That is, the amount of wrinkles and spots varies depending on the person even at the same age. For example, people who currently have a large amount of stains and wrinkles tend to have a large decrease in stains and wrinkles due to aging, and a small increase in stains and wrinkles due to aging. Change ζ. Conversely, people who currently have few wrinkle / wrinkle components tend to have less decrease in wrinkle / wrinkle components when they age, and there is a tendency for the amount of increase in wrinkle / wrinkle components to increase with age or to maintain the current basis. Yes, the adjustment rate ζ is changed accordingly.

  In this way, according to the amount of the stain / wrinkle component of the acquired image, the adjustment rate ζ of the stain / wrinkle component in the aging image / aged image creation is changed, and this is reflected in the adjustment coefficient ρ. Thus, a more accurate aging / aging image can be created.

  Further, the adjustment coefficient ρ may be changed as shown in the following formula (14) according to the adjustment rate η indicating the presence or absence of makeup.

ρ = β (S0) × α × γ × δ × η (14)
That is, the amount of visible wrinkles and spots varies considerably depending on the presence or absence of makeup. For example, when makeup is applied at the time of acquisition of the current age image, the wrinkle component / stain component extracted tends to decrease. Therefore, the adjustment rate η is increased and the adjustment coefficient ρ is increased. On the other hand, when creating an aging / aging image in the state of makeup, the adjustment factor ρ is reduced by decreasing the adjustment rate η at the time of aging / aging so that the wrinkle component / stain component is less than the actual amount. Make it smaller. In this way, by taking into account the presence or absence of makeup in the acquired image, or the presence or absence of makeup when creating an aging / aging image, by changing the adjustment factor ρ of the stain component / wrinkle component, more accurate aging / Aged images can be created.

  In the equations (13) and (14), the case where the adjustment rates ζ and η are used separately is exemplified, but the adjustment coefficient ρ = β (S0) × α × γ × δ × ζ × η As described above, the adjustment coefficient ρ may be calculated using the adjustment rates ζ and η.

  Furthermore, in the said embodiment, although illustrated about the case where the 2nd database 140 is comprised by the combination of one set of database A, B, C, for example, data table A, B according to the color of skin. , C may have a plurality of combinations. That is, the appearance of the stain component and the wrinkle component tends to differ depending on the skin color. For example, when the skin is dark, changes in the stain and wrinkle components due to changes in age are not so noticeable. On the other hand, when the skin is white, changes in the stain component and the wrinkle component due to age change are conspicuous. Therefore, for example, a plurality of combinations of the data tables A, B, and C are prepared according to the skin color, and the adjustment coefficient ρ based on the increase / decrease tendency of the wrinkle component / stain component according to the skin color, or the adjustment rate α, γ , Δ, ζ, and η can be used to create a more accurate aging / aging image.

The block diagram which shows the structure of the authentication apparatus used as embodiment of this invention The block diagram which shows the structure of the authentication part 100 in the authentication apparatus of embodiment shown in FIG. The block diagram which shows the structure of the image generation part 60 in the authentication part 100 shown in FIG. FIG. 3 is a block diagram showing the configuration of the blurred image creation means 10 in the image generation unit 60 shown in FIG. The figure which shows the example of the one-dimensional filter F which the filtering means 12 in the blur image creation means 10 shown in FIG. 4 uses The figure which shows the process performed in the blur image creation means 10 shown in FIG. The figure which shows the frequency characteristic of the filtering image Bk produced by the filtering means 12 in the blur image creation means 10 shown in FIG. The figure which shows the example of the two-dimensional filter used by the filtering means 12 in the blur image creation means 10 shown in FIG. The figure which shows the example of the filter F1 which the interpolation means 14 in the blur image creation means 10 shown in FIG. 4 uses for interpolation of filtering image B1 The figure which shows the example of the filter F2 which the interpolation means 14 in the blur image creation means 10 shown in FIG. 4 uses for interpolation of filtering image B2 The figure which shows the frequency characteristic of the blur image Sk created by the blur image creation means 10 shown in FIG. The figure which shows the frequency characteristic of the band limited image Tk produced by the band limited image preparation means 20 in the image generation part 60 shown in FIG. The figure which shows the example of the nonlinear function f which the wrinkle component extraction means 30 in the image generation part 60 shown in FIG. 3 uses The block diagram which shows the structure of the aged image preparation means 40 in the image generation part 60 shown in FIG. The figure which shows the content of the 1st database 120 The figure which shows the content of the 2nd database 140 The flowchart which shows the process in the authentication apparatus shown in FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Image pick-up part 2 Input part 3 Object identification means 5 YCC conversion means 10 Blurred image creation means 12 Filtering means 14 Interpolation means 16 Control means 20 Band-limited image creation means 30 Wrinkle component extraction means 40 Aging image creation means 42 Current age calculation part 44 Parameter Setting Unit 46 Creation Execution Unit 50 Composition Unit 60 Image Generation Unit 70 Verification Unit 100 Authentication Unit 120 First Database 140 Second Database D0 Face Image D1 Aging Image Dg Registered Face Image Y Luminance Value Cb, Cr Color Difference Value α coefficient γ0 adjustment rate γ final adjustment rate δ0 adjustment rate for each part δ final adjustment rate for each part β pixel value dependent coefficient ρ adjustment coefficient

Claims (33)

Using an image of a skin part of a person of a predetermined age as an actual-age image, an aging image that becomes an image of the skin part after aging of the person and / or an image of the skin part at the time of aging of the person In an image creation method for creating an aged image that becomes
Extracting from the current age image as an age component a component capable of showing a skin condition that increases with an increase in age,
Adjusting the age component with a predetermined adjustment strength to obtain an adjustment component,
An image creation method comprising: adding the adjustment component to the current age image in creating the aging image; and subtracting the adjustment component from the current image in creating the aging image.   The image creation method according to claim 1, wherein the age component is a wrinkle component and / or a stain component. Based on the age image, create a plurality of band limited images representing components for each of the frequency bands of the age image,
For an input value in which the absolute value of the output value is less than or equal to the absolute value of the input value and the absolute value is less than or equal to a predetermined threshold value, the absolute value of the output value increases as the absolute value of the input value increases. On the other hand, for an input value whose absolute value is larger than the predetermined threshold value, nonlinear conversion processing in which the absolute value of the output value is equal to or smaller than the absolute value of the output value corresponding to the predetermined threshold value is performed for each band limitation. Apply to each pixel value of the image to get the pixel values of multiple converted images,
3. The image creation method according to claim 2, wherein an added pixel value obtained by adding pixel values of corresponding pixels of the plurality of converted images is obtained as a pixel value of an age component image representing the age component. .   4. The image creation method according to claim 3, wherein an image value of an image representing the adjustment component is obtained by multiplying a pixel value of the age component image by an adjustment coefficient indicating the adjustment intensity.   The image creation method according to claim 4, wherein the adjustment coefficient is determined for each pixel in accordance with a pixel value of a pixel of the age image.   The image creation method according to claim 1, wherein the adjustment strength is such that the adjustment component increases as the degree of aging or aging increases.   The image creation method according to claim 6, wherein the adjustment intensity is determined according to an age group of the aging period or the aging period.   8. The image creation method according to claim 1, wherein the adjustment strength is determined in accordance with a portion of the person's body where the skin portion is.   9. The image creation method according to claim 1, wherein the adjustment strength is determined in accordance with a degree of the age component extracted from the current age image.   10. The adjustment strength according to claim 1, wherein the adjustment strength is determined according to presence / absence of makeup in the current age image or presence / absence of makeup at the time of creation of the aging image or the aged image. The image creation method according to any one of the preceding claims.   The image creation method according to claim 1, wherein the adjustment strength is determined according to a skin color of the person. Using an image of a skin part of a person of a predetermined age as an actual-age image, an aging image that becomes an image of the skin part after aging of the person and / or an image of the skin part at the time of aging of the person In an image creation device that creates an aged image that becomes
Age component extraction means for extracting from the current age image as an age component a component capable of showing a skin condition that increases with an increase in age;
Adjustment component acquisition means for adjusting the age component at a predetermined adjustment intensity to obtain an adjustment component;
Image adjustment means for acquiring the aging image by adding the adjustment component to the current age image, and subtracting the adjustment component from the current age image to acquire the aging image. A featured image creation device.   The image creating apparatus according to claim 12, wherein the age component is a wrinkle component and / or a stain component. The age component extraction means is
Based on the age image, create a plurality of band limited images representing components for each of a plurality of frequency bands of the age image,
For an input value in which the absolute value of the output value is less than or equal to the absolute value of the input value and the absolute value is less than or equal to a predetermined threshold value, the absolute value of the output value increases as the absolute value of the input value increases. On the other hand, for an input value whose absolute value is larger than the predetermined threshold value, nonlinear conversion processing in which the absolute value of the output value is equal to or smaller than the absolute value of the output value corresponding to the predetermined threshold value is performed for each band limitation. Apply to each pixel value of the image to get the pixel values of multiple converted images,
The acquired pixel value obtained by adding pixel values of corresponding pixels of the plurality of converted images is acquired as a pixel value of an age component image representing the age component. Image creation device.   15. The adjustment component acquisition unit according to claim 14, wherein the adjustment component acquisition unit obtains an image value of an image representing the adjustment component by multiplying a pixel value of the age component image by an adjustment coefficient indicating the adjustment intensity. Image creation device.   The image creation apparatus according to claim 15, wherein the adjustment coefficient is determined for each pixel in accordance with a pixel value of a pixel of the age image.   17. The image creating apparatus according to claim 12, wherein the adjustment strength is such that the adjustment component increases as the degree of aging or aging increases.   The image creating apparatus according to claim 17, wherein the adjustment strength is determined according to an age group of the aging period or the aging period.   The image creation apparatus according to claim 12, wherein the adjustment strength is determined in accordance with a part of the person's body where the skin portion is.   20. The image creating apparatus according to claim 12, wherein the adjustment strength is determined according to a degree of the age component extracted from the current age image.   21. The adjustment intensity according to claim 12, wherein the adjustment intensity is determined according to presence / absence of makeup in the current age image or presence / absence of makeup at the time of creation of the aging image or the aged image. The image creation apparatus of any one of Claims.   The image creation apparatus according to any one of claims 12 to 21, wherein the adjustment strength is determined according to a skin color of the person. Using an image of a skin part of a person of a predetermined age as an actual-age image, an aging image that becomes an image of the skin part after aging of the person and / or an image of the skin part at the time of aging of the person A program for causing a computer to execute an image creation process for creating an aged image to be
The image creation process is an age component extraction process for extracting from the current age image as an age component a component that can indicate a skin condition that increases with an increase in age;
An adjustment component acquisition process for adjusting the age component with a predetermined adjustment intensity to obtain an adjustment component;
The image processing includes: adding the adjustment component to the current age image to obtain the aging image; and subtracting the adjustment component from the current age image to obtain the aged image. program.   The program according to claim 23, wherein the age component is a wrinkle component and / or a stain component. The age component extraction process is
Based on the age image, create a plurality of band limited images representing components for each of a plurality of frequency bands of the age image,
For an input value in which the absolute value of the output value is less than or equal to the absolute value of the input value and the absolute value is less than or equal to a predetermined threshold value, the absolute value of the output value increases as the absolute value of the input value increases. On the other hand, for an input value whose absolute value is larger than the predetermined threshold value, nonlinear conversion processing in which the absolute value of the output value is equal to or smaller than the absolute value of the output value corresponding to the predetermined threshold value is performed for each band limitation. Apply to each pixel value of the image to get the pixel values of multiple converted images,
25. The processing according to claim 24, wherein the added pixel value obtained by adding pixel values of corresponding pixels of the plurality of converted images is acquired as a pixel value of an age component image representing the age component. program.   The adjustment component acquisition process is a process of obtaining an image value of an image representing the adjustment component by multiplying a pixel value of the age component image by an adjustment coefficient indicating the adjustment intensity. program.   27. The program according to claim 26, wherein the adjustment coefficient is determined for each of the pixels according to a pixel value of a pixel of the age image.   The program according to any one of claims 23 to 27, wherein the adjustment strength is such that the adjustment component increases as the degree of aging or aging increases.   29. The program according to claim 28, wherein the adjustment strength is determined according to an age group of the aging period or the aging period.   30. The program according to any one of claims 23 to 29, wherein the adjustment strength is determined according to a part of the person's body where the skin portion is.   The program according to any one of claims 23 to 30, wherein the adjustment strength is determined according to a degree of the age component extracted from the current age image.   32. The adjustment strength according to claim 23, wherein the adjustment intensity is determined according to presence / absence of makeup in the current age image or presence / absence of makeup at the time of creation of the aging image or the aged image. The program according to any one of the above.   The program according to any one of claims 23 to 32, wherein the adjustment intensity is determined according to a skin color of the person.

Images